Jim Gettys writes:
Most operating schedulers are much happier to give you the CPU
again if you don't monopolize the CPU, and let the other processes
get the CPU regularly. Generally, they boost the priority
of processes that just use a short amount of CPU, and then
give it back.
Can we at least agree to export an xf86Yield() function? It
will be sched_yield() on whatever plaforms support it, a noop on
others. If somebody comes up with something better to implement
it with, then great.
Mark.
___
Mark Vojkovich wrote:
Can we at least agree to export an xf86Yield() function? It
will be sched_yield() on whatever plaforms support it, a noop on
others. If somebody comes up with something better to implement
it with, then great.
I have no voice on that but still : I think this would
Nathan Hand wrote:
Why not
slice 1) send 1 megabyte
...
slice 2) fifo not drained, reduce fifo to 512kB, wait
...
slice 3) fifo not drained, reduce fifo to 256kB, wait
...
slice 4) fifo drained, send 256kB
...
slice 5) fifo
Mark Vojkovich writes:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never returns in less than 10 msec which has the effect of making
Mark Vojkovich writes:
Your experience is out of date. If I've just filled a Megabyte
DMA fifo and I'm waiting to cram another Megabyte into it, how
quick is my FIFO busy loop then? I've had great success with
sched_yield().
The DMA buffer case may be different than the video
Most operating schedulers are much happier to give you the CPU
again if you don't monopolize the CPU, and let the other processes
get the CPU regularly. Generally, they boost the priority
of processes that just use a short amount of CPU, and then
give it back.
This is typical interactive
--- Egbert Eich [EMAIL PROTECTED] a écrit : Mark
Vojkovich writes:
Can we export to the drivers some function that
yields the CPU?
Currently alot of drivers burn the CPU waiting
for fifos, etc...
usleep(0) is not good for this because it's jiffy
based and usually
never returns
info on futexes:
http://ds9a.nl/futex-manpages/
I'm not real familiar with them.
Alex
--- Mark Vojkovich [EMAIL PROTECTED] wrote:
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD wrote:
This is perhaps a dumb idea, but could the futexes
help here? I don't know if they have equivalent
--- Mark Vojkovich [EMAIL PROTECTED] a écrit :
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD
wrote:
This is perhaps a dumb idea, but could the futexes
help here? I don't know if they have equivalent on
other OSes than Linux.
Bye
Manu
I don't see how they help. The problem
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD wrote:
I'm assuming futexes are some interprocess mutex
mechanism?
If so, I don't see how this helps.
Yes it is. Actually I am not familiar with them
either, but if you had a way to be able to wake up
your waiting process ASAP
--- Mark Vojkovich [EMAIL PROTECTED] a écrit :
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD
wrote:
I'm assuming futexes are some interprocess
mutex
mechanism?
If so, I don't see how this helps.
Yes it is. Actually I am not familiar with them
either, but if
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD wrote:
The problem with yielding is that you can have
interactivity problem if the computer is loaded
enough.
If you don't yield you have an interactivity problem.
What good is keeping your time slices if all you're doing
during them is
--- Mark Vojkovich [EMAIL PROTECTED] a écrit :
On Tue, 23 Sep 2003, [iso-8859-1] emmanuel ALLAUD
wrote:
The problem with yielding is that you can have
interactivity problem if the computer is loaded
enough.
If you don't yield you have an interactivity
problem.
What good is
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never returns in less than 10 msec which has the effect of making
interactivity worse instead of
Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never returns in less than 10 msec which has the effect of making
Ian Romanick wrote (in a message from Monday 22)
Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never
On Tue, 2003-09-23 at 05:58, Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never returns in less than 10 msec which has
On Mon, 22 Sep 2003, Ian Romanick wrote:
Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never returns in less
On Tue, 23 Sep 2003, Nathan Hand wrote:
On Tue, 2003-09-23 at 05:58, Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
On Tue, 2003-09-23 at 07:55, Mark Vojkovich wrote:
On Tue, 23 Sep 2003, Nathan Hand wrote:
On Tue, 2003-09-23 at 05:58, Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0)
Mark Vojkovich wrote:
On Mon, 22 Sep 2003, Ian Romanick wrote:
Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
usleep(0) is not good for this because it's jiffy based and usually
never
Nathan Hand wrote:
On Tue, 2003-09-23 at 07:55, Mark Vojkovich wrote:
On Tue, 23 Sep 2003, Nathan Hand wrote:
On Tue, 2003-09-23 at 05:58, Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn the CPU waiting for fifos, etc...
On Tue, 23 Sep 2003, Nathan Hand wrote:
On Tue, 2003-09-23 at 07:55, Mark Vojkovich wrote:
On Tue, 23 Sep 2003, Nathan Hand wrote:
On Tue, 2003-09-23 at 05:58, Mark Vojkovich wrote:
Can we export to the drivers some function that yields the CPU?
Currently alot of drivers burn
24 matches
Mail list logo
